A learning system can occupy execution states that are indistinguishable under every declared present-behavior readout yet respond differently to future training. We formalize this through fiber fingerprints: controlled future-learning response laws restricted to present-behavior equivalence classes.
arXiv:2608. 10172v1 Announce Type: new Abstract: Mechanistic interpretability explains models by identifying circuits inside them, but has no way to tell whether a circuit is a property of the model or an artifact of the method that found it.
By Ashim Dhor, Pin-Yu Chen
Revelation Control studies how to price interventions that reveal hidden state only when the revealed distinctions can alter a consequential decision, while separately accounting for any useful progress the intervention itself creates. The authors develop a framework for learning systems that defines decision‑sufficient revelation, revelation depth, and a cost‑adjusted factorization criterion, and they provide a target‑independent protocol for model‑specific instantiation. Experiments on Qwen2.5‑7B and Mistral‑7B‑v0.3 show that deeper future‑learning probes have positive decision value and that productive reuse yields strict equal‑compute utility advantages, supporting a structural transfer of the decision theory and evaluation protocol across architectures.
By Qinyou Wang
arXiv:2607. 04333v1 Announce Type: new Abstract: Grokking -- generalization arriving long after training-set interpolation -- can be accelerated by structure-agnostic interventions: gradient filtering, weight-norm clamping, geometric penalties on hidden representations.
By Gunner Levi Howe
arXiv:2609. 23366v1 Announce Type: new Abstract: Recurrent models must preserve information that changes future behavior while suppressing hidden-state error.
By Linzhe Zhang, Changming Xu
arXiv:2512. 18471v2 Announce Type: replace Abstract: Continual learning systems face a fundamental geometric obstacle: as experience accumulates on a fixed-capacity manifold, covering numbers grow linearly with time, eventually forcing representational overlap and catastrophic interference.
By Xin Li